© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 11675
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Comey"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of James Comey

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fiji
    -0.73
     Mond
    -0.72
    ¥µ
    -0.70
    AIDS
    -0.67
    emonic
    -0.67
    piring
    -0.67
    tips
    -0.66
    Disney
    -0.66
    cer
    -0.65
    istan
    -0.65
    POSITIVE LOGITS
    agher
    0.90
     testified
    0.88
     Comey
    0.85
    vernment
    0.83
     memos
    0.82
     testifying
    0.81
     Clapper
    0.79
     favors
    0.74
     exoner
    0.73
     resigned
    0.71
    Activations Density 0.031%

    No Known Activations